Enhanced Prediction and Characterization of CDK Inhibitors Using Optimal Class Distribution

Cyclin-dependent kinase inhibitors (CDKIs) govern the regulation of cyclin-dependent kinases, which are responsible for controlling cell cycle progression. The members of the CDKI protein family play important roles in many processes like tumor suppression, apoptosis, transcriptional regulation. The sequence similarity-based search methods to annotate putative CDKIs do not yield optimal performance due to sequence diversity of CDKIs. As a consequence, machine learning-based models have become viable choices for predicting CDKI. In this work, we have developed a framework for handling the class imbalance factor (which is encountered very frequently in biological datasets) in order to enhance the prediction of CDKI through machine learning approaches. We have designed our experiments to achieve the optimal performance of machine learning-based methods in predicting CDKI by investigating the dataset-related prediction enhancement issues, like: (1) What should be the optimal class distribution ratio in the training set? (2) Should we oversample or undersample? (3) At what ratio, positive and negative samples should be oversampled or undersampled? and (4) How to select the best-performing classifier? We have addressed these issues through comparing the results from an imbalanced training set with training sets which are created at different resampling rates by using synthetic minority over-sampling technique and undersampling technique to have varied class distributions. The proposed framework resulted in 100 % sensitivity, 93.7 % specificity, 96.4 % accuracy, 0.929 MCC with 0.981 AUC using simple sequence-based features on a leave-one-out cross-validation test. The generalization ability of the trained model was further tested on four separate blind testing sets. Our work supports the fact that the performance of the algorithms can be enhanced by creating an optimal class distribution in the training set besides fine-tuning of the parameters of the algorithms. This optimal ratio of positive and negative samples in the training set is an important learning enhancement parameter for prediction models based on machine learning algorithms.